Update Oct. 21st: The transcription portion of the post has been updated, what I originally mistook as issues with how the data was formatted was an issue with too many tokens in the transcript I wanted transcribed. At this point we all know how LLMs can generate text, and I’m guessing that everybody reading this …

Read More

What you are reading now is the fourth iteration of this post, which has gone through multiple revisions and re-considerations. It might feel a bit fragmented, but my aim is to provide a comprehensive post covering two related topics. The first part will discuss my experimentation with local LLMs (large language …

Read More